Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NOMARJ/sigil --skill data-context-extractorgit clone --depth 1 https://github.com/NOMARJ/sigilWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nomarj/sigil/data-context-extractor)<a href="https://agentmods.dev/skills/nomarj/sigil/data-context-extractor"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/data-context-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nomarj/sigil/data-context-extractor"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/data-context-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.00684 |
| Opus 5.5 | $0.00036 | $0.00274 |
| Sonnet 5.5 | $0.00018 | $0.00137 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
data-context-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Context Extractor
Build a project-specific data skill that teaches Claude your company's data warehouse, terminology, metrics definitions, and common query patterns. Two modes:
Bootstrap Mode
Trigger: No existing data context skill for this project.
Process
-
Schema Discovery
- If database access available: query
information_schemaor equivalent - If not: ask user to paste/upload schema, ERD, or table descriptions
- Discover: tables, columns, types, relationships, row counts
- If database access available: query
-
Tribal Knowledge Interview (ask these questions):
- What are the 5 most common queries your analysts run?
- What metrics does the business track? How are they calculated?
- What's the grain of each major table? (one row = one what?)
- Are there any gotchas? (deleted rows not actually deleted, timezone mismatches, denormalized fields)
- What terminology does the team use that wouldn't be obvious? (internal names, abbreviations)
- What's the data freshness? (real-time, hourly, daily, weekly)
- Which tables join to which? What are the common join patterns?
-
Generate the Skill Write a
data-context/SKILL.mdin the project's.claude/skills/(or.nomark/data/) containing:- Schema summary (tables, key columns, grain, relationships)
- Metrics dictionary (metric name → SQL definition)
- Common query patterns (templated SQL for frequent questions)
- Gotchas and caveats
- Terminology glossary
- Data freshness expectations
Iteration Mode
Trigger: Existing data context skill needs updating.
Process
- Load existing skill
- Ask targeted questions about the gap (new table, new metric, changed business logic)
- Update the relevant section
- Note the change in an amendment log
Output Format
# Data Context — [Project Name]
## Schema Overview
| Table | Grain | Key Columns | Freshness | Notes |
|-------|-------|-------------|-----------|-------|
## Metrics Dictionary
| Metric | Definition (SQL) | Business Context |
|--------|-----------------|-----------------|
## Common Query Patterns
### [Question type]
```sql
-- Template query
Gotchas
- [Gotcha 1]
- [Gotcha 2]
Terminology
| Term | Meaning |
|---|
Amendment Log
| Date | Change | Author |
|---|
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 92 lines · 91 tokens per session scan A 891bececb9b0
data-context-extractor is a skill published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 91 tokens to every session and 684 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
can
A debugging tool for CAN and CAN-FD, communication systems used by vehicles and embedded devices. It can find interfaces, monitor and send messages, record logs, decode DBC database files, and report bus statistics.
huawei-cloud-modelarts-notebook-management
Manage Huawei Cloud ModelArts Notebook instances through full lifecycle operations via hcloud CLI. Covers 31 API interfaces across 7 functional domains: instance management (create/list/show/update/delete/start/stop), lease management (show/renew), tag management (show/create/delete), image management…
data-pipeline
ETL/ELT pipeline design. Trigger when the user wants to create data flows, transformations, or orchestration.
azure-ai-transcription-py
Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.
harness-optimizer
Use this skill when tuning AI agent configurations for performance, cost, and reliability. Covers token optimization, context window management, model selection, prompt engineering for agents, and ...
prompt_engineering
Expert guide on prompt engineering for 2024-2025 models (GPT-4o, Claude 3.5, o1, o3, Gemini 2.0). Covers reasoning models, delimiters, structured output, and context engineering.